minchaoh2002/Qwen3-14B-PragReST

Partial fine-tune vs Qwen/Qwen3-14B. Partial change: 89% of the weights changed (attention, mlp, norms), in 40 of 40 layers.

Tensors changed: Embeddings 0/1, Norms 105/161, MLP 120/120, Attention 160/160, lm_head 0/1

2 derivatives checked

• mradermacher/Qwen3-14B-PragReST-i1-GGUF: Quantization
• mradermacher/Qwen3-14B-PragReST-GGUF: Quantization

On the Hub · Downloads on Model Pulse